© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 5775
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "handling" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     McClure
    -0.79
     ferien
    -0.73
     Rees
    -0.73
     Biggs
    -0.68
     vaga
    -0.67
     bytu
    -0.67
     Schmitz
    -0.66
     Clough
    -0.64
    Sheep
    -0.63
    Oat
    -0.63
    POSITIVE LOGITS
     handling
    2.91
     handled
    2.68
     Handling
    2.68
    handling
    2.59
     handles
    2.58
     handle
    2.47
    Handling
    2.45
     Handles
    2.41
     Handle
    2.40
    handled
    2.31
    Activations Density 0.045%

    No Known Activations